Matches in SemOpenAlex for { <https://semopenalex.org/work/W63957208> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W63957208 abstract "When we look at a familiar object from a novel viewpoint, we are usually able to recognize it. In this thesis, we address the problem of learning to recognize objects under transformations associated with viewpoint. Our vision model combines a hierarchical representation of shape features with an explicit representation of the transformation. Shape features are represented in a layered pyramid-shaped subnetwork, while the transformation is explicitly represented in an auxiliary subnetwork. The two connectionist networks are conjunctively combined to allow object-centered shape features to be computed in the upper layers of the network. A simulation of a 2-D translation subnetwork demonstrates the ability to learn to recognize shapes in different locations in an image, such that those same shapes can be recognized in novel locations.Two new learning methods are presented, which provide improved behavior over previous backpropagation methods. Both methods involve competitive interactions among clusters of nodes. The new learning methods demonstrate improved learning over the generalized delta rule when applied to a number of network tasks.In the first method, called error modification, competition is based on the error signals computed from the gradient of the output error. The result of this competition is a set of modified error signals representing a contrast enhanced version of the original errors. The error modification method reduces the occurrence of network configurations that correspond to local error minima.In the second method, called error augmentation, competition is based on the activations of the nodes in the cluster. Network changes resulting from this competition augment those specified by the error gradient computation. This competition is implemented by the trace comparison rule, a new self-organizing mechanism that is effective in developing highly discriminating features within the cluster. The error augmentation method improves learning in the lower network layers when backpropagated error is weak." @default.
- W63957208 created "2016-06-24" @default.
- W63957208 creator A5024048378 @default.
- W63957208 date "1987-01-01" @default.
- W63957208 modified "2023-09-23" @default.
- W63957208 title "Learning object-centered representations" @default.
- W63957208 hasPublicationYear "1987" @default.
- W63957208 type Work @default.
- W63957208 sameAs 63957208 @default.
- W63957208 citedByCount "1" @default.
- W63957208 crossrefType "journal-article" @default.
- W63957208 hasAuthorship W63957208A5024048378 @default.
- W63957208 hasConcept C103278499 @default.
- W63957208 hasConcept C104317684 @default.
- W63957208 hasConcept C11413529 @default.
- W63957208 hasConcept C115961682 @default.
- W63957208 hasConcept C142575187 @default.
- W63957208 hasConcept C153180895 @default.
- W63957208 hasConcept C154945302 @default.
- W63957208 hasConcept C155032097 @default.
- W63957208 hasConcept C177264268 @default.
- W63957208 hasConcept C17744445 @default.
- W63957208 hasConcept C185592680 @default.
- W63957208 hasConcept C199360897 @default.
- W63957208 hasConcept C199539241 @default.
- W63957208 hasConcept C204241405 @default.
- W63957208 hasConcept C2524010 @default.
- W63957208 hasConcept C2776359362 @default.
- W63957208 hasConcept C2780186347 @default.
- W63957208 hasConcept C2781238097 @default.
- W63957208 hasConcept C33923547 @default.
- W63957208 hasConcept C38652104 @default.
- W63957208 hasConcept C41008148 @default.
- W63957208 hasConcept C50644808 @default.
- W63957208 hasConcept C55493867 @default.
- W63957208 hasConcept C80444323 @default.
- W63957208 hasConcept C8521452 @default.
- W63957208 hasConcept C94625758 @default.
- W63957208 hasConceptScore W63957208C103278499 @default.
- W63957208 hasConceptScore W63957208C104317684 @default.
- W63957208 hasConceptScore W63957208C11413529 @default.
- W63957208 hasConceptScore W63957208C115961682 @default.
- W63957208 hasConceptScore W63957208C142575187 @default.
- W63957208 hasConceptScore W63957208C153180895 @default.
- W63957208 hasConceptScore W63957208C154945302 @default.
- W63957208 hasConceptScore W63957208C155032097 @default.
- W63957208 hasConceptScore W63957208C177264268 @default.
- W63957208 hasConceptScore W63957208C17744445 @default.
- W63957208 hasConceptScore W63957208C185592680 @default.
- W63957208 hasConceptScore W63957208C199360897 @default.
- W63957208 hasConceptScore W63957208C199539241 @default.
- W63957208 hasConceptScore W63957208C204241405 @default.
- W63957208 hasConceptScore W63957208C2524010 @default.
- W63957208 hasConceptScore W63957208C2776359362 @default.
- W63957208 hasConceptScore W63957208C2780186347 @default.
- W63957208 hasConceptScore W63957208C2781238097 @default.
- W63957208 hasConceptScore W63957208C33923547 @default.
- W63957208 hasConceptScore W63957208C38652104 @default.
- W63957208 hasConceptScore W63957208C41008148 @default.
- W63957208 hasConceptScore W63957208C50644808 @default.
- W63957208 hasConceptScore W63957208C55493867 @default.
- W63957208 hasConceptScore W63957208C80444323 @default.
- W63957208 hasConceptScore W63957208C8521452 @default.
- W63957208 hasConceptScore W63957208C94625758 @default.
- W63957208 hasLocation W639572081 @default.
- W63957208 hasOpenAccess W63957208 @default.
- W63957208 hasPrimaryLocation W639572081 @default.
- W63957208 hasRelatedWork W1167987884 @default.
- W63957208 hasRelatedWork W1493335204 @default.
- W63957208 hasRelatedWork W1988068846 @default.
- W63957208 hasRelatedWork W1989200976 @default.
- W63957208 hasRelatedWork W2007326887 @default.
- W63957208 hasRelatedWork W2100570425 @default.
- W63957208 hasRelatedWork W2141729354 @default.
- W63957208 hasRelatedWork W2144526807 @default.
- W63957208 hasRelatedWork W2146444479 @default.
- W63957208 hasRelatedWork W2149010456 @default.
- W63957208 hasRelatedWork W2151389371 @default.
- W63957208 hasRelatedWork W2152503286 @default.
- W63957208 hasRelatedWork W2156170757 @default.
- W63957208 hasRelatedWork W2228202129 @default.
- W63957208 hasRelatedWork W2560082610 @default.
- W63957208 hasRelatedWork W2765456303 @default.
- W63957208 hasRelatedWork W2962920843 @default.
- W63957208 hasRelatedWork W2970027214 @default.
- W63957208 hasRelatedWork W2980839814 @default.
- W63957208 hasRelatedWork W3013007011 @default.
- W63957208 isParatext "false" @default.
- W63957208 isRetracted "false" @default.
- W63957208 magId "63957208" @default.
- W63957208 workType "article" @default.